social-carousel

Pass

Audited by Gen Agent Trust Hub on Oct 19, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external inputs such as design tokens from a DESIGN.md file and user-provided captions to generate its output. While this creates a potential surface for indirect prompt injection, the risk is negligible as the skill's capabilities are limited to generating static HTML and CSS artifacts without any execution or file-system access privileges.
  • [EXTERNAL_DOWNLOADS]: The provided example implementation references external typography resources from Google Fonts (fonts.googleapis.com and fonts.gstatic.com). These are well-known and trusted services commonly used for web styling and do not represent a security risk in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 19, 2026, 06:23 PM